© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 89485
    Prev
    Next
    INDEX
    Explanations

    instances of confusion and questioning in personal narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Phrases that introduce explanations or reasons for problems, typically appearing at the beginning of questions or statements that seek to explain why something isn't working as expected.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kitt
    -0.06
    TypeInfo
    -0.06
    اخ
    -0.06
    _critical
    -0.06
    ASIC
    -0.06
    slashes
    -0.06
    reated
    -0.06
    ARGV
    -0.06
    thermal
    -0.06
    ì¹
    -0.06
    POSITIVE LOGITS
    åİŁåĽł
    0.13
     Causes
    0.12
     blame
    0.12
     causes
    0.12
     reasons
    0.11
     Explanation
    0.11
     blames
    0.11
     blaming
    0.11
     blamed
    0.11
     explanation
    0.11
    Activations Density 0.166%

    No Known Activations